BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Who is Afraid of Non-Universal (Deep Learned) Facial Perception? -
  Dr Pablo Barros\, SONY R&amp\;D CENTER\, BRUSSELS LABORATORY (BRL)\, BELG
 IUM
DTSTART:20220913T100000Z
DTEND:20220913T110000Z
UID:TALK178571@talks.cam.ac.uk
CONTACT:104848
DESCRIPTION:Facial Expression Recognition (FER) has become a popular topic
  within the hyper-active computer vision community\, which has led to the 
 development of a plethora of FER solutions easily accessible to the genera
 l public. In most cases\, based on deep learned facial expression represen
 tations. Such solutions became the backbone of human-based interaction res
 earch\, being used as means for human behavior analysis\, the backbone for
  interaction-driven models\, and one of the most fundamental blocks of pro
 posed cognitive architectures. Most of these important research rely blind
 ly on the objective performance of FER systems\, and their capability to c
 ategorize a face\, in most cases even on a frame-level\, into one known an
 d pre-determined emotional category. Once you actually understand how deep
 -learned FER models actually categorize faces\, it is easy to see that tru
 sting on their outputs might bias drastically all of the previously mentio
 ned research areas. These models are trained mostly in a supervised task\,
  where groups of pixels are pushed to compose a specific and pre-determine
 d emotional category. In most cases\, these affective labels are deeply co
 nnected to the scenario represented by the datasets these models were trai
 ned on\, which changes drastically the interpretation of their FER results
 . Similarly to the recent advents on non-universal facial perception\, und
 erstanding the context in which these models were trained might help to av
 oid a strong bias in their application on fundamental research\, and help 
 us to be more responsible in our claims and findings. The goal of this tal
 k is to discuss the core of the problem of trusting blindly FER systems\, 
 and to foster a discussion on the importance of understanding their functi
 oning. In this regard\, I will present our most recent research on facial 
 expression perception and hot we can address the biasing of affective cate
 gorization based on the non-universal perception theory\, and how this can
  impact in future use of FER technology to other fields.
LOCATION:SS03
END:VEVENT
END:VCALENDAR